1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
"""
Isotonic Regression Example.
"""
from __future__ import print_function
from pyspark import SparkContext
# $example on$
import math
from pyspark.mllib.regression import LabeledPoint, IsotonicRegression, IsotonicRegressionModel
from pyspark.mllib.util import MLUtils
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="PythonIsotonicRegressionExample")
# $example on$
# Load and parse the data
def parsePoint(labeledData):
return (labeledData.label, labeledData.features[0], 1.0)
data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_isotonic_regression_libsvm_data.txt")
# Create label, feature, weight tuples from input data with weight set to default value 1.0.
parsedData = data.map(parsePoint)
# Split data into training (60%) and test (40%) sets.
training, test = parsedData.randomSplit([0.6, 0.4], 11)
# Create isotonic regression model from training data.
# Isotonic parameter defaults to true so it is only shown for demonstration
model = IsotonicRegression.train(training)
# Create tuples of predicted and real labels.
predictionAndLabel = test.map(lambda p: (model.predict(p[1]), p[0]))
# Calculate mean squared error between predicted and real labels.
meanSquaredError = predictionAndLabel.map(lambda pl: math.pow((pl[0] - pl[1]), 2)).mean()
print("Mean Squared Error = " + str(meanSquaredError))
# Save and load model
model.save(sc, "target/tmp/myIsotonicRegressionModel")
sameModel = IsotonicRegressionModel.load(sc, "target/tmp/myIsotonicRegressionModel")
# $example off$
|